Figma

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Figma integration that uses Membrane for authenticated Figma access, with expected but sensitive abilities to read and change Figma data.

Install only if you trust Membrane and intend to connect it to your Figma account. Prefer prebuilt read-only actions when possible, confirm exact file/comment targets before posting or deleting anything or using POST/PUT/PATCH/DELETE proxy requests, and revoke the Membrane/Figma connection when you no longer need it.

SkillSpector

By NVIDIA

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill advertises destructive actions like deleting comments and posting comments without any caution, confirmation, or requirement for explicit user consent. In an agent setting, this increases the risk of unintended state changes in a user's Figma workspace, especially if the model infers action from ambiguous prompts.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal